Agreeableness in AI personas reliably predicts sycophantic behavior in 9 of 13 tested language models.
Minicpm4: Ultra-efficient llms on end devices
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
representative citing papers
ReverseEOL improves training-free text embeddings by combining forward and reversed-text representations from frozen decoder-only LLMs.
SparDA introduces a decoupled Forecast head per GQA group in sparse attention to enable lookahead KV selection and prefetching, delivering up to 1.25x prefill and 1.7x decode speedups with matched accuracy on 8B models.
DashAttention introduces differentiable adaptive sparse hierarchical attention via α-entmax block selection, achieving full-attention accuracy at 75% sparsity with improved Pareto performance over NSA and InfLLMv2.
TIDE-Bench is a new benchmark for tool-integrated reasoning that combines diverse tasks, multi-aspect metrics covering answer quality, process reliability, efficiency and cost, plus filtered challenging test sets.
MiniCPM-o 4.5 uses the Omni-Flow streaming framework to deliver real-time full-duplex omni-modal interaction with proactive behavior in a 9B model that approaches Gemini 2.5 Flash performance.
Kimi Linear hybridizes linear attention with a new KDA module to beat full attention on tasks while slashing KV cache by 75% and speeding decoding up to 6x.
VoxCPM2 scales hierarchical continuous-latent speech modeling to 2B parameters and over 2M hours of multilingual data, unifying voice cloning, style control, and continuation in one backbone with open release.
JaiTTS-v1.0 achieves 1.94% CER on short Thai speech, beating human ground truth of 1.98%, matches humans on long speech, and wins 283 of 400 human comparisons against commercial systems.
LongAct uses saliency from high-magnitude activations to guide sparse weight updates in long-context RL, yielding about 8% gains on LongBench v2 across multiple algorithms.
POLIS gets 1-4B parameter language models to verify each other's math answers, store the good ones in shared memory, and fine-tune on them, reporting big average gains, but the protocol is underspecified.
citing papers explorer
-
Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models
Agreeableness in AI personas reliably predicts sycophantic behavior in 9 of 13 tested language models.
-
ReverseEOL: Improving Training-free Text Embeddings via Text Reversal in Decoder-only LLMs
ReverseEOL improves training-free text embeddings by combining forward and reversed-text representations from frozen decoder-only LLMs.
-
SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference
SparDA introduces a decoupled Forecast head per GQA group in sparse attention to enable lookahead KV selection and prefetching, delivering up to 1.25x prefill and 1.7x decode speedups with matched accuracy on 8B models.
-
DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention
DashAttention introduces differentiable adaptive sparse hierarchical attention via α-entmax block selection, achieving full-attention accuracy at 75% sparsity with improved Pareto performance over NSA and InfLLMv2.
-
TIDE-Bench: Task-Aware and Diagnostic Evaluation of Tool-Integrated Reasoning
TIDE-Bench is a new benchmark for tool-integrated reasoning that combines diverse tasks, multi-aspect metrics covering answer quality, process reliability, efficiency and cost, plus filtered challenging test sets.
-
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
MiniCPM-o 4.5 uses the Omni-Flow streaming framework to deliver real-time full-duplex omni-modal interaction with proactive behavior in a 9B model that approaches Gemini 2.5 Flash performance.
-
Kimi Linear: An Expressive, Efficient Attention Architecture
Kimi Linear hybridizes linear attention with a new KDA module to beat full attention on tasks while slashing KV cache by 75% and speeding decoding up to 6x.
-
VoxCPM2 Technical Report
VoxCPM2 scales hierarchical continuous-latent speech modeling to 2B parameters and over 2M hours of multilingual data, unifying voice cloning, style control, and continuation in one backbone with open release.
-
JaiTTS: A Thai Voice Cloning Model
JaiTTS-v1.0 achieves 1.94% CER on short Thai speech, beating human ground truth of 1.98%, matches humans on long speech, and wins 283 of 400 human comparisons against commercial systems.
-
LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning
LongAct uses saliency from high-magnitude activations to guide sparse weight updates in long-context RL, yielding about 8% gains on LongBench v2 across multiple algorithms.
-
The Ratchet Effect in Silico: How Interaction Drives Cumulative Intelligence in Large Language Models
POLIS gets 1-4B parameter language models to verify each other's math answers, store the good ones in shared memory, and fine-tune on them, reporting big average gains, but the protocol is underspecified.